GPT-5.6 Sol
openai/gpt-5.6-sol
Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
Capabilities
ReasoningYes
Tool callingYes
Structured outputYes
TemperatureFixed
AttachmentYes
Open weightsNo
Limits
Context1,050,000 tokens
Max input922,000 tokens
Max output128,000 tokens
Details
Familygpt-sol
Knowledge cutoff2026-02-16
Release date2026-07-09
Last updated2026-07-09
Modalities
Inputtext, image, pdf
Outputtext
Benchmarks
SWE-Bench Pro
64.6
resolve rate
Terminal-Bench
88.8
success rate
DeepSWE
72.7
resolve rate
GPQA Diamond
94.6
accuracy
FrontierMath
89
accuracy
BrowseComp
90.4
accuracy
OSWorld
62.6
success rate
MMMU Pro
83
accuracy
Agents' Last Exam
52.7
Toolathlon
58
success rate
Artificial Analysis Intelligence Index
58.9
index score
Artificial Analysis Coding Agent Index
80
index score
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A